Voice processing method and device, electronic equipment and storage medium

• Main Authors: LIU HAIBO, ZHANG BIN, YANG YUECHEN, WANG ZHENLI, WANG QI, WANG TONG, SUN ZHIZHOU, WANG WANGUO, SUN ANQING, SUN XIAOBIN, ZHANG ZHI, XU KANG, WANG XINGZHAO, GUO RUI, MENG HAILEI
• Format: Patent
• Language: Chinese; English
• Published: 06.12.2022
• Subjects: ACOUSTICS; MUSICAL INSTRUMENTS; PHYSICS; SPEECH ANALYSIS OR SYNTHESIS; SPEECH OR AUDIO CODING OR DECODING; SPEECH OR VOICE PROCESSING; SPEECH RECOGNITION

The invention discloses a voice processing method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring inspection voice information to be recognized in an electric power inspection process; processing the inspection voice information based on the inspection voice acoustic model to obtain a character recognition result corresponding to each audio frame in the inspection voice information; and processing each character recognition result based on the target decoded graph to obtain a target inspection text corresponding to the inspection voice information. The problem that in the prior art, the accuracy of electric power inspection professional term recognition based on a general voice recognition model is low is solved, the voice recognition accuracy is improved, the electric power inspection voice recognition requirement is met, and inspection work quality improvement and efficiency improvement are assisted. 本发明公开了一种语音处理方法、装置、电子设备及存储介质。该方法包括：获取电力巡检过程中待识别的巡检